Model Reference Adaptive Control of Semi-active Suspension Model Based on AdaBoost Algorithm for Rollover Prediction

Due to their large volume structure, when a heavy vehicle encounters sudden road conditions, emergency turns, or lane changes, it is very easy for vehicle rollover accidents to occur; however, well-designed suspension systems can greatly reduce vehicle rollover occurrence. In this article, a novel semi-active suspension adaptive control based on AdaBoost algorithm is proposed to effectively improve the vehicle rollover stability under dangerous working conditions. This research first established a vehicle rollover warning model based on the AdaBoost algorithm. Meanwhile, the approximate skyhook damping suspension model is established as the reference model of the semi-active suspension. Furthermore, the model reference adaptive control (MRAC) system is established based on Lyapunov stability theory, and the adaptive controller is designed. Finally, on the same road condition, the rollover warning control simulations are carried out under the following conditions: the 180-degree step, the fishhook, and the double-lane-change condition. Simulation results show that the proposed reference adaptive control based on the AdaBoost algorithm for rollover control can effectively predict vehicle rollover in early warning and improve the anti-rollover capability of vehicles.